Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    action verbs and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Zel
    0.50
     Fall
    0.48
     cookbook
    0.43
     Sil
    0.43
     Cook
    0.42
     Jacobson
    0.42
     hot
    0.42
     Gal
    0.41
     Ded
    0.41
     Per
    0.41
    POSITIVE LOGITS
     број
    0.50
     전에
    0.49
     иннова
    0.47
     výraz
    0.46
     није
    0.46
     ถึง
    0.46
     يجب
    0.45
    Inicio
    0.45
     effectué
    0.45
    цы
    0.44
    Act Density 0.001%

    No Known Activations